Statistical Projections for Multi-resolution, Multi-dimensional Visual Data Exploration and Analysis

doi:10.2172/1235087

GSTDTAP > 地球科学

DOI	10.2172/1235087
报告编号	LBNL--1003958
来源ID	OSTI ID: 1235087
	Statistical Projections for Multi-resolution, Multi-dimensional Visual Data Exploration and Analysis
	Hoa T. Nguyen; Stone, Daithi; E. Wes Bethel
	2016
出版年	2016
页数	7
语种	英语
国家	美国
领域	地球科学
英文摘要	An ongoing challenge in visual exploration and analysis of large, multi-dimensional datasets is how to present useful, concise information to a user for some specific visualization tasks. Typical approaches to this problem have proposed either reduced-resolution versions of data, or projections of data, or both. These approaches still have some limitations such as consuming high computation or suffering from errors. In this work, we explore the use of a statistical metric as the basis for both projections and reduced-resolution versions of data, with a particular focus on preserving one key trait in data, namely variation. We use two different case studies to explore this idea, one that uses a synthetic dataset, and another that uses a large ensemble collection produced by an atmospheric modeling code to study long-term changes in global precipitation. The primary findings of our work are that in terms of preserving the variation signal inherent in data, that using a statistical measure more faithfully preserves this key characteristic across both multi-dimensional projections and multi-resolution representations than a methodology based upon averaging.
英文关键词	nonparmetric statistics visualizing data variation information interfaces and presentation multi-variate multi-resolution projection simulation and modeling simulation output analysis
URL	查看原文
来源平台	US Department of Energy (DOE)
引用统计
文献类型	科技报告
条目标识符	http://119.78.100.173/C666/handle/2XK7JSWQ/7380
专题	地球科学
推荐引用方式 GB/T 7714	Hoa T. Nguyen,Stone, Daithi,E. Wes Bethel. Statistical Projections for Multi-resolution, Multi-dimensional Visual Data Exploration and Analysis,2016.